The why, what, and how of AI-based coding in scientific research

TL;DR

This paper explores how large language models can transform scientific coding by providing guidance on their roles, types of assistance, and practical workflows, aiming to improve research efficiency and education.

Contribution

It offers a comprehensive framework detailing the roles, assistance types, and workflows of AI-based coding, with practical strategies for researchers.

Findings

Identifies six types of AI coding assistance.

Proposes a five-step workflow for AI integration in coding.

Addresses limitations and future directions of AI in scientific coding.

Abstract

Computer programming (coding) is indispensable for researchers across disciplines, yet it remains challenging to learn and time-consuming to carry out. Generative AI, particularly large language models (LLMs), has the potential to transform coding into intuitive conversations, but best practices and effective workflows are only emerging. We dissect AI-based coding through three key lenses: the nature and role of LLMs in coding (why), six types of coding assistance they provide (what), and a five-step workflow in action with practical implementation strategies (how). Additionally, we address the limitations and future outlook of AI in coding. By offering actionable insights, this framework helps to guide researchers in effectively leveraging AI to enhance coding practices and education, accelerating scientific progress.